Picture for Feijun Jiang

Feijun Jiang

CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite

Add code
Mar 18, 2024
Figure 1 for CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite
Figure 2 for CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite
Figure 3 for CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite
Figure 4 for CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite
Viaarxiv icon

A unified multichannel far-field speech recognition system: combining neural beamforming with attention based end-to-end model

Add code
Jan 05, 2024
Viaarxiv icon

Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder

Add code
Aug 14, 2023
Figure 1 for Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder
Figure 2 for Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder
Figure 3 for Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder
Figure 4 for Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder
Viaarxiv icon

Network Pruning Spaces

Add code
Apr 19, 2023
Figure 1 for Network Pruning Spaces
Figure 2 for Network Pruning Spaces
Figure 3 for Network Pruning Spaces
Figure 4 for Network Pruning Spaces
Viaarxiv icon

McQueen: a Benchmark for Multimodal Conversational Query Rewrite

Add code
Oct 23, 2022
Figure 1 for McQueen: a Benchmark for Multimodal Conversational Query Rewrite
Figure 2 for McQueen: a Benchmark for Multimodal Conversational Query Rewrite
Figure 3 for McQueen: a Benchmark for Multimodal Conversational Query Rewrite
Figure 4 for McQueen: a Benchmark for Multimodal Conversational Query Rewrite
Viaarxiv icon

Bootstrap Latent Representations for Multi-modal Recommendation

Add code
Jul 13, 2022
Figure 1 for Bootstrap Latent Representations for Multi-modal Recommendation
Figure 2 for Bootstrap Latent Representations for Multi-modal Recommendation
Figure 3 for Bootstrap Latent Representations for Multi-modal Recommendation
Figure 4 for Bootstrap Latent Representations for Multi-modal Recommendation
Viaarxiv icon

iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis based on Disentanglement between Prosody and Timbre

Add code
Jun 29, 2022
Figure 1 for iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis based on Disentanglement between Prosody and Timbre
Figure 2 for iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis based on Disentanglement between Prosody and Timbre
Figure 3 for iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis based on Disentanglement between Prosody and Timbre
Figure 4 for iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis based on Disentanglement between Prosody and Timbre
Viaarxiv icon

NER-BERT: A Pre-trained Model for Low-Resource Entity Tagging

Add code
Dec 01, 2021
Figure 1 for NER-BERT: A Pre-trained Model for Low-Resource Entity Tagging
Figure 2 for NER-BERT: A Pre-trained Model for Low-Resource Entity Tagging
Figure 3 for NER-BERT: A Pre-trained Model for Low-Resource Entity Tagging
Figure 4 for NER-BERT: A Pre-trained Model for Low-Resource Entity Tagging
Viaarxiv icon

BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling

Add code
Jun 05, 2021
Figure 1 for BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling
Figure 2 for BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling
Figure 3 for BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling
Figure 4 for BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling
Viaarxiv icon